Sets up AI Signals binary classification (propensity scoring) on Treasure Data for churn, lead scoring, conversion, campaign response, upsell or renewal. Builds leakage-safe stacked training snapshots, trains XGBoost/CatBoost with tuning, threshold selection and SHAP, writes Parent Segment scores, and builds the project agent and dashboard. Use to start, configure, change, re-run or resume a project or rebuild its agent. Trigger on: set up a propensity model, start a propensity project, ai signals propensity model, propensity model, propensity scoring, how does propensity model work, predict which customers will churn, score leads by likelihood to convert, predict campaign response, build a churn model, build a lead scoring model, classifier setup, classification workflow, configure the classifier, classifier data prep, training snapshots, classifier output tables, rebuild the classifier agent, resume classifier setup, classifier runbook. Project agents answer performance, drivers and scores questions.